Model comparison
Inkling vs Qwen3.5-Flash
Inkling is the stronger model overall, scoring 44.1 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 15× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Inkling scores higher in 7 categories and Qwen3.5-Flash in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 43.2.
- The biggest single-benchmark swing is SimpleQA Verified: 40.3% for Inkling and 20.3% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Qwen3.5-Flash accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Qwen3.5-Flash | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 42.3 |
| Released | 2026-07-15 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 66K | 1M |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.87 | $0.10 |
| Output $ / M tokens | $4.68 | $0.40 |
| Results tracked | 41 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Inkling: 34.1 (#229), Qwen3.5-Flash: 33.9 (#234)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1412 | 1243 |
| LMArena Coding | 1463 | 1412 |
| ALE-Bench | 946 | 221.8 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
Agentic & Tool Use Not comparable
Inkling: 29.5 (#76), Qwen3.5-Flash: —
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Inkling leads
Inkling: 40.6 (#48), Qwen3.5-Flash: 32.9 (#63)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 21% | 21% |
| LMArena Hard Prompts | 1452 | 1404 |
| DTBench | 87.5% | 82.9% |
| LMCA | 37.6% | 29.1% |
| Epoch Capabilities Index | 148.6 | 143.98 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Mystery Game Puzzles | — | 20% |
Math Qwen3.5-Flash leads
Inkling: 31.2 (#198), Qwen3.5-Flash: 36.3 (#117)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 18.2% |
| OTIS Mock AIME 2024-2025 | 88.9% | 84.4% |
| LMArena Math | 1482 | 1407 |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Inkling leads
Inkling: 55.2 (#44), Qwen3.5-Flash: 43.2 (#84)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 88.3% | 82.3% |
| SimpleQA Verified | 40.3% | 20.3% |
| LMArena Expert | 1468 | 1408 |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Inkling leads
Inkling: 54.2 (#49), Qwen3.5-Flash: 50.7 (#116)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1434 | 1385 |
| LMArena Chinese | 1495 | 1446 |
| LMArena French | 1453 | 1412 |
| LMArena German | 1456 | 1389 |
| LMArena Japanese | 1428 | 1369 |
| LMArena Korean | 1401 | 1344 |
| LMArena Russian | 1430 | 1379 |
| LMArena Spanish | 1442 | 1399 |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Qwen3.5-Flash: 72.8 (#133)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1427 | 1374 |
Long Context Inkling leads
Inkling: 43.9 (#79), Qwen3.5-Flash: 42.4 (#119)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1436 | 1392 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Qwen3.5-Flash: 58.2 (#117)
| Benchmark | Inkling | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1443 | 1397 |
| LMArena Creative Writing | 1390 | 1343 |
| LMArena Multi-Turn | 1436 | 1393 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen3.5-Flash?
Inkling is the stronger model overall, scoring 44.1 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 15× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Qwen3.5-Flash better for coding?
They score almost the same on coding (34.1 vs 33.9); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 66K.
How many benchmarks do Inkling and Qwen3.5-Flash share?
27 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3.5-Flash has 32.